Record Details

Classification of place of articulation in unvoiced stops with spectro-temporal surface modeling

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Classification of place of articulation in unvoiced stops with spectro-temporal surface modeling
 
Creator KARJIGI, V
RAO, P
 
Subject Place of articulation
Unvoiced stops
Spectro-temporal features
SPEECH RECOGNITION
CONSONANTS
PERCEPTION
FEATURES
UTTERANCES
 
Description Unvoiced stops are rapidly varying sounds with acoustic cues to place identity linked to the temporal dynamics. Neurophysiological studies have indicated the importance of joint spectro-temporal processing in the human perception of stops. In this study, two distinct approaches to modeling the spectra-temporal envelope of unvoiced stop phone segments are investigated with a view to obtaining a low-dimensional feature vector for automatic place classification. Classification accuracies on the TIMIT database and a Marathi words dataset show the overall superiority of classifier combination of polynomial surface coefficients and 2D-DCT. A comparison of performance with published results on the place classification of stops revealed that the proposed spectro-temporal feature systems improve upon the best previous systems' performances. The results indicate that joint spectro-temporal features may be usefully incorporated in hierarchical phone classifiers based on diverse class-specific features. (c) 2012 Elsevier B.V. All rights reserved.
 
Publisher ELSEVIER SCIENCE BV
 
Date 2014-10-16T06:55:11Z
2014-10-16T06:55:11Z
2012
 
Type Article
 
Identifier SPEECH COMMUNICATION, 54(10)1104-1120
http://dx.doi.org/10.1016/j.specom.2012.04.007
http://dspace.library.iitb.ac.in/jspui/handle/100/15487
 
Language en